OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
We present OLMoTrace, the first system that traces the outputs of language models back to their full, multi-trillion-token training data in real time. OLMoTrace finds and shows verbatim matches between segments of language model output and documents in the training text corpora. Powered by an extended version of infini-gram (Liu et al., 2024), our system returns tracing results within a few seconds. OLMoTrace can help users understand the behavior of language models through the lens of their training data. We showcase how it can be used to explore fact checking, hallucination, and the creativity of language models. OLMoTrace is publicly available and fully open-source.
Code (0)
등록된 구현이 없습니다.
Tasks
Fact CheckingHallucinationLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions
The responses generated by Large Language Models (LLMs) can include sensitive information from individuals and organizations, leading to potential privacy leakage. This work implements Influence Functions (IFs) to trace …
Contrastive Error Attribution for Finetuned Language Models
Recent work has identified noisy and misannotated data as a core cause of hallucinations and unfaithful outputs in Natural Language Generation (NLG) tasks. Consequently, identifying and removing these examples is a key o…
Text GenerationText SummarizationExpert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models
Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to layers or feed-forward modules. Sparse mixture-of-experts (MoE) langu…
From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education
Knowledge Tracing (KT) is a critical component in online learning, but traditional approaches face limitations in interpretability and cross-domain adaptability. This paper introduces Language Model-based Code Knowledge …
Knowledge TracingLanguage ModelingLanguage ModellingScalable Influence and Fact Tracing for Large Language Model Pretraining
Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model tran…
AttributeLanguage ModelingLanguage ModellingLarge Language Model